Interpreting Safety Outcomes: Waymo's Performance Evaluation in the Context of a Broader Determination of Safety Readiness

2023/06/23 by Francesca Favarò, Trent Victor, Favaro, Francesca M. +5 · 2 citations
Decision Sciences · Health Professions · Psychology · #FOS: Computer and information sciences #Human-Automation Interaction and Safety #Occupational Health and Safety Research #Risk and Safety Analysis #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.2306.14923

openalex publication_date 2023/06/23 · openalex created_date 2023/06/30 · openalex updated_date 2026/07/28

Abstract

This paper frames recent publications from Waymo within the broader context of the safety readiness determination for an Automated Driving System (ADS). Starting from a brief overview of safety performance outcomes reported by Waymo (i.e., contact events experienced during fully autonomous operations), this paper highlights the need for a diversified approach to safety determination that complements the analysis of observed safety outcomes with other estimation techniques. Our discussion highlights: the presentation of a "credibility paradox" within the comparison between ADS crash data and human-derived baselines; the recognition of continuous confidence growth through in-use monitoring; and the need to supplement any aggregate statistical analysis with appropriate event-level reasoning.

Cited by

• TARGET setting for high severity collisions: tolerance-based assessment of risk for generalized event thresholds
• Determining Absence of Unreasonable Risk: Approval Guidelines for an Automated Driving System Deployment

Related

• Building a Credible Case for Safety: Waymo's Approach for the Determination of Absence of Unreasonable Risk
• Waymo's Safety Methodologies and Safety Readiness Determinations
• Collision Avoidance Testing of the Waymo Automated Driving System
• Assessing a Safety Case: Bottom-up Guidance for Claims and Evidence Evaluation
• Waymo Public Road Safety Performance Data